---
language:
- ro
license: apache-2.0
base_model: openai/whisper-small
tags:
- hf-asr-leaderboard
- generated_from_trainer
metrics:
- wer
model-index:
- name: Whisper Small Ro - VM5
  results: []
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# Whisper Small Ro - VM5

This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4022
- Wer: 20.5014

## Model description

More information needed

## Intended uses & limitations

More information needed

## Training and evaluation data

More information needed

## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 150
- training_steps: 4000

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer     |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
| 0.2624        | 1.86  | 1000 | 0.3680          | 23.1297 |
| 0.0494        | 3.72  | 2000 | 0.3680          | 21.1803 |
| 0.0086        | 5.59  | 3000 | 0.3935          | 20.9316 |
| 0.0043        | 7.45  | 4000 | 0.4022          | 20.5014 |


### Framework versions

- Transformers 4.32.0.dev0
- Pytorch 2.1.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3